linux-kernel - Re: [PATCH v8 06/12] mmc: mmc_test: test to measure how sg

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <BANLkTimuvUcJyrO0S+Odmz2Vz0YDwyY9Mw@mail.gmail.com>
Date:	Fri, 1 Jul 2011 15:33:19 +0200
From:	Per Forlin <per.forlin@...aro.org>
To:	linaro-dev@...ts.linaro.org,
	Nicolas Pitre <nicolas.pitre@...aro.org>,
	linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org,
	linux-mmc@...r.kernel.org,
	Nickolay Nickolaev <nicknickolaev@...il.com>,
	Venkatraman S <svenkatr@...com>,
	Linus Walleij <linus.walleij@...aro.org>
Cc:	Chris Ball <cjb@...top.org>, Per Forlin <per.forlin@...aro.org>
Subject: Re: [PATCH v8 06/12] mmc: mmc_test: test to measure how sg_len affect performance

On 28 June 2011 10:11, Per Forlin <per.forlin@...aro.org> wrote:
> test that measures how the mmc bandwidth depends on the numbers of sg elements
> in the sg list. The transfer size if fixed and sg length goes from a few up
> to 512. The purpose is to measure overhead caused by multiple sg elements.
>
> Signed-off-by: Per Forlin <per.forlin@...aro.org>
> ---
>  drivers/mmc/card/mmc_test.c |  151 +++++++++++++++++++++++++++++++++++++++----
>  1 files changed, 139 insertions(+), 12 deletions(-)
>
> diff --git a/drivers/mmc/card/mmc_test.c b/drivers/mmc/card/mmc_test.c
> -static int mmc_test_map_sg(struct mmc_test_mem *mem, unsigned long sz,
> +static int mmc_test_map_sg(struct mmc_test_mem *mem, unsigned long size,
>                           struct scatterlist *sglist, int repeat,
>                           unsigned int max_segs, unsigned int max_seg_sz,
> -                          unsigned int *sg_len)
> +                          unsigned int *sg_len, int min_sg_len)
>  {
>        struct scatterlist *sg = NULL;
>        unsigned int i;
> +       unsigned long sz = size;
>
>        sg_init_table(sglist, max_segs);
> +       if (min_sg_len > max_segs)
> +               min_sg_len = max_segs;
>
>        *sg_len = 0;
>        do {
>                for (i = 0; i < mem->cnt; i++) {
>                        unsigned long len = PAGE_SIZE << mem->arr[i].order;
>
> +                       if (min_sg_len && (size / min_sg_len < len))
> +                               len = size / min_sg_len;
Make aligned to 512
len = ALIGN(size / min_sg_len, 512);

I run into this issue running on arm realview with max test size 128k
instead of 128M.

/Per
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/